A Fast Scenario Transfer Approach for Portrait Styles Through Collaborative Awareness of Convolutional Neural Network and Generative Adversarial Learning

• Published in: Journal of circuits, systems, and computers Vol. 33; no. 7
• Main Authors: Wang, Yajie, Liang, Shaolin
• Format: Journal Article
• Language: English
• Published: Singapore World Scientific Publishing Company 15.05.2024; World Scientific Publishing Co. Pte., Ltd
• Subjects: Algorithms; Artificial neural networks; Collaboration; Feature extraction; Feature maps; Image manipulation; Image processing; Machine learning; Neural networks; Workflow; intelligent algorithm; fast scenario transfer; Convolutional neural network; generative adversarial learning; portrait style
• ISSN: 0218-1266; 1793-6454
• DOI: 10.1142/S0218126624501214

The fast scenario transfer for portrait styles has been a universal concern in the area of image processing. Conventionally, it was realized mostly by manual manipulation based on expertise experience, which costs a large amount of human labor. To fit the growing business volume in the era of Internet 4.0, it is supposed to investigate reliable autonomous workflow that generates portrait-style results via intelligent algorithms. Therefore, this paper proposes a fast scenario transfer method for portrait styles through collaborative awareness of convolutional neural network (CNN) and generative learning (GAL). On the one hand, a CNN structure is designed to make feature extraction towards the initial images, which can be used for following image generation. On the other hand, the GAL is utilized to generate new images with post-transferred scenario styles, so that the expected scenario style transfer results can be output by generating new images through long-term iterations. Especially, the loss function is designed by simultaneously considering local and global characteristics. Finally, the analysis and experimental results show that the correction process can be completed by injecting the extracted input face features into the feature maps of corresponding sizes in the generation process using a pre-trained feature extractor. Thus, the face conversion efficiency can be improved.